	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 64.6%	1st 66.1%	- -	3rd 62.5%	5th 59.7%	4th 61.0%
62.8%	69%	63%		68%	53%	61%
73.8%	72%	70%		73%	72%	82%
89.0%	95%	95%		86%	86%	83%
55.6%	66%	63%		52%	46%	51%
55.2%	65%	43%		51%	43%	74%
64.6%	67%	62%		67%	68%	59%
64.0%	72%	65%		62%	65%	56%
63.6%	75%	86%		47%	60%	50%
50.6%	53%	62%		47%	41%	50%
50.8%	48%	55%		44%	58%	49%
84.2%	87%	86%		83%	83%	82%
81.2%	79%	66%		90%	86%	85%
50.4%	61%	68%		58%	27%	38%
71.2%	76%	74%		65%	75%	66%
79.2%	85%	73%		72%	84%	82%
86.6%	88%	94%		88%	74%	89%
53.8%	55%	61%		58%	55%	40%
72.0%	75%	84%		74%	68%	59%
40.4%	39%	48%		46%	20%	49%
65.2%	67%	79%		54%	62%	64%
63.4%	61%	60%		57%	70%	69%
77.6%	83%	85%		75%	74%	71%
39.0%	40%	44%		34%	46%	31%
63.6%	65%	50%		68%	68%	67%
70.8%	71%	73%		71%	66%	73%
83.8%	83%	86%		86%	82%	82%
86.4%	90%	79%		88%	93%	82%
59.2%	68%	66%		55%	61%	46%
72.4%	75%	67%		80%	70%	70%
44.4%	46%	54%		39%	28%	55%
77.6%	75%	86%		86%	79%	62%
48.8%	44%	42%		51%	49%	58%
49.0%	48%	58%		47%	47%	45%
64.0%	65%	66%		62%	57%	70%
26.2%	21%	33%		30%	24%	23%
83.2%	79%	89%		86%	86%	76%
67.0%	74%	74%		59%	67%	61%
24.4%	27%	28%		19%	28%	20%
75.6%	76%	71%		77%	77%	77%
63.8%	56%	75%		59%	69%	60%
73.2%	74%	81%		62%	84%	65%
58.8%	60%	68%		48%	67%	51%
46.2%	38%	57%		48%	42%	46%
73.0%	81%	76%		80%	68%	60%
81.0%	75%	84%		85%	73%	88%
32.4%	26%	38%		29%	20%	49%
32.4%	34%	28%		51%	13%	36%
52.6%	61%	55%		49%	53%	45%
54.8%	55%	69%		51%	50%	49%
53.2%	54%	58%		64%	28%	62%
73.6%	83%	75%		73%	64%	73%
63.4%	66%	57%		64%	65%	65%
84.6%	91%	89%		88%	73%	82%
57.8%	52%	52%		70%	57%	58%